摘要
离散Hopfield神经网络是一类特殊的反馈网络,可广泛应用于联想记忆设计、组合优化计算等方面.反馈神经网络的稳定性不仅被认为是神经网络最基本的问题之一,同时也是神经网络各种应用的基础.为此,利用状态转移方程和定义能量函数的方法,研究离散Hopfield神经网络在部分并行演化模式下的渐近行为,并举例说明了一个已有结论是错误的,同时给出了一些新的网络收敛于稳定状态的充分条件.所获结果进一步推广了一些已有的结论.
The discrete Hopfield neural network is a special kind of feedback neural networks. The stability of recurrent neural networks is not only known to be one of the mostly basic problems, but also known to be bases of the network various applications. The dynamic behavior of discrete Hopfield neural network is mainly studied in partial parallel mode by the use of the state transition equation and the energy function. One counter-example is given to illustrate one previous result in reference being error, and some new sufficient conditions for the networks converging towards stable states are investigated. The obtained results here further generalize some existing results on stability of the networks.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第2期230-233,共4页
Control and Decision
基金
中国博士后科学基金项目(2003033516)
国家自然科学基金优秀创新研究群体基金项目(70121001).
